1 ------------------------------------------------------------------------------
2 T H E /proc F I L E S Y S T E M
3 ------------------------------------------------------------------------------
4 /proc/sys Terrehon Bowden <terrehon@pacbell.net> October 7 1999
5 Bodo Bauer <bb@ricochet.net>
7 2.4.x update Jorge Nerin <comandante@zaralinux.com> November 14 2000
8 move /proc/sys Shen Feng <shen@cn.fujitsu.com> April 1 2009
9 ------------------------------------------------------------------------------
10 Version 1.3 Kernel version 2.2.12
11 Kernel version 2.4.0-test11-pre4
12 ------------------------------------------------------------------------------
13 fixes/update part 1.1 Stefani Seibold <stefani@seibold.net> June 9 2009
19 0.1 Introduction/Credits
22 1 Collecting System Information
23 1.1 Process-Specific Subdirectories
25 1.3 IDE devices in /proc/ide
26 1.4 Networking info in /proc/net
28 1.6 Parallel port info in /proc/parport
29 1.7 TTY info in /proc/tty
30 1.8 Miscellaneous kernel statistics in /proc/stat
31 1.9 Ext4 file system parameters
33 2 Modifying System Parameters
35 3 Per-Process Parameters
36 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj - Adjust the oom-killer
38 3.2 /proc/<pid>/oom_score - Display current oom-killer score
39 3.3 /proc/<pid>/io - Display the IO accounting fields
40 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
41 3.5 /proc/<pid>/mountinfo - Information about mounts
42 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm
43 3.7 /proc/<pid>/task/<tid>/children - Information about task children
44 3.8 /proc/<pid>/fdinfo/<fd> - Information about opened file
45 3.9 /proc/<pid>/map_files - Information about memory mapped files
46 3.10 /proc/<pid>/timerslack_ns - Task timerslack value
51 ------------------------------------------------------------------------------
53 ------------------------------------------------------------------------------
55 0.1 Introduction/Credits
56 ------------------------
58 This documentation is part of a soon (or so we hope) to be released book on
59 the SuSE Linux distribution. As there is no complete documentation for the
60 /proc file system and we've used many freely available sources to write these
61 chapters, it seems only fair to give the work back to the Linux community.
62 This work is based on the 2.2.* kernel version and the upcoming 2.4.*. I'm
63 afraid it's still far from complete, but we hope it will be useful. As far as
64 we know, it is the first 'all-in-one' document about the /proc file system. It
65 is focused on the Intel x86 hardware, so if you are looking for PPC, ARM,
66 SPARC, AXP, etc., features, you probably won't find what you are looking for.
67 It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But
68 additions and patches are welcome and will be added to this document if you
71 We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of
72 other people for help compiling this documentation. We'd also like to extend a
73 special thank you to Andi Kleen for documentation, which we relied on heavily
74 to create this document, as well as the additional information he provided.
75 Thanks to everybody else who contributed source or docs to the Linux kernel
76 and helped create a great piece of software... :)
78 If you have any comments, corrections or additions, please don't hesitate to
79 contact Bodo Bauer at bb@ricochet.net. We'll be happy to add them to this
82 The latest version of this document is available online at
83 http://tldp.org/LDP/Linux-Filesystem-Hierarchy/html/proc.html
85 If the above direction does not works for you, you could try the kernel
86 mailing list at linux-kernel@vger.kernel.org and/or try to reach me at
87 comandante@zaralinux.com.
92 We don't guarantee the correctness of this document, and if you come to us
93 complaining about how you screwed up your system because of incorrect
94 documentation, we won't feel responsible...
96 ------------------------------------------------------------------------------
97 CHAPTER 1: COLLECTING SYSTEM INFORMATION
98 ------------------------------------------------------------------------------
100 ------------------------------------------------------------------------------
102 ------------------------------------------------------------------------------
103 * Investigating the properties of the pseudo file system /proc and its
104 ability to provide information on the running Linux system
105 * Examining /proc's structure
106 * Uncovering various information about the kernel and the processes running
108 ------------------------------------------------------------------------------
111 The proc file system acts as an interface to internal data structures in the
112 kernel. It can be used to obtain information about the system and to change
113 certain kernel parameters at runtime (sysctl).
115 First, we'll take a look at the read-only parts of /proc. In Chapter 2, we
116 show you how you can use /proc/sys to change settings.
118 1.1 Process-Specific Subdirectories
119 -----------------------------------
121 The directory /proc contains (among other things) one subdirectory for each
122 process running on the system, which is named after the process ID (PID).
124 The link self points to the process reading the file system. Each process
125 subdirectory has the entries listed in Table 1-1.
128 Table 1-1: Process specific entries in /proc
129 ..............................................................................
131 clear_refs Clears page referenced bits shown in smaps output
132 cmdline Command line arguments
133 cpu Current and last cpu in which it was executed (2.4)(smp)
134 cwd Link to the current working directory
135 environ Values of environment variables
136 exe Link to the executable of this process
137 fd Directory, which contains all file descriptors
138 maps Memory maps to executables and library files (2.4)
139 mem Memory held by this process
140 root Link to the root directory of this process
142 statm Process memory status information
143 status Process status in human readable form
144 wchan Present with CONFIG_KALLSYMS=y: it shows the kernel function
145 symbol the task is blocked in - or "0" if not blocked.
147 stack Report full stack trace, enable via CONFIG_STACKTRACE
148 smaps a extension based on maps, showing the memory consumption of
149 each mapping and flags associated with it
150 numa_maps an extension based on maps, showing the memory locality and
151 binding policy as well as mem usage (in pages) of each mapping.
152 ..............................................................................
154 For example, to get the status information of a process, all you have to do is
155 read the file /proc/PID/status:
157 >cat /proc/self/status
182 SigPnd: 0000000000000000
183 ShdPnd: 0000000000000000
184 SigBlk: 0000000000000000
185 SigIgn: 0000000000000000
186 SigCgt: 0000000000000000
187 CapInh: 00000000fffffeff
188 CapPrm: 0000000000000000
189 CapEff: 0000000000000000
190 CapBnd: ffffffffffffffff
192 voluntary_ctxt_switches: 0
193 nonvoluntary_ctxt_switches: 1
195 This shows you nearly the same information you would get if you viewed it with
196 the ps command. In fact, ps uses the proc file system to obtain its
197 information. But you get a more detailed view of the process by reading the
198 file /proc/PID/status. It fields are described in table 1-2.
200 The statm file contains more detailed information about the process
201 memory usage. Its seven fields are explained in Table 1-3. The stat file
202 contains details information about the process itself. Its fields are
203 explained in Table 1-4.
205 (for SMP CONFIG users)
206 For making accounting scalable, RSS related information are handled in an
207 asynchronous manner and the value may not be very precise. To see a precise
208 snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
209 It's slow but very precise.
211 Table 1-2: Contents of the status files (as of 4.1)
212 ..............................................................................
214 Name filename of the executable
215 State state (R is running, S is sleeping, D is sleeping
216 in an uninterruptible wait, Z is zombie,
217 T is traced or stopped)
219 Ngid NUMA group ID (0 if none)
221 PPid process id of the parent process
222 TracerPid PID of process tracing this process (0 if not)
223 Uid Real, effective, saved set, and file system UIDs
224 Gid Real, effective, saved set, and file system GIDs
225 FDSize number of file descriptor slots currently allocated
226 Groups supplementary group list
227 NStgid descendant namespace thread group ID hierarchy
228 NSpid descendant namespace process ID hierarchy
229 NSpgid descendant namespace process group ID hierarchy
230 NSsid descendant namespace session ID hierarchy
231 VmPeak peak virtual memory size
232 VmSize total program size
233 VmLck locked memory size
234 VmHWM peak resident set size ("high water mark")
235 VmRSS size of memory portions
236 VmData size of data, stack, and text segments
237 VmStk size of data, stack, and text segments
238 VmExe size of text segment
239 VmLib size of shared library code
240 VmPTE size of page table entries
241 VmPMD size of second level page tables
242 VmSwap size of swap usage (the number of referred swapents)
243 HugetlbPages size of hugetlb memory portions
244 Threads number of threads
245 SigQ number of signals queued/max. number for queue
246 SigPnd bitmap of pending signals for the thread
247 ShdPnd bitmap of shared pending signals for the process
248 SigBlk bitmap of blocked signals
249 SigIgn bitmap of ignored signals
250 SigCgt bitmap of caught signals
251 CapInh bitmap of inheritable capabilities
252 CapPrm bitmap of permitted capabilities
253 CapEff bitmap of effective capabilities
254 CapBnd bitmap of capabilities bounding set
255 Seccomp seccomp mode, like prctl(PR_GET_SECCOMP, ...)
256 Cpus_allowed mask of CPUs on which this process may run
257 Cpus_allowed_list Same as previous, but in "list format"
258 Mems_allowed mask of memory nodes allowed to this process
259 Mems_allowed_list Same as previous, but in "list format"
260 voluntary_ctxt_switches number of voluntary context switches
261 nonvoluntary_ctxt_switches number of non voluntary context switches
262 ..............................................................................
264 Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
265 ..............................................................................
267 size total program size (pages) (same as VmSize in status)
268 resident size of memory portions (pages) (same as VmRSS in status)
269 shared number of pages that are shared (i.e. backed by a file)
270 trs number of pages that are 'code' (not including libs; broken,
271 includes data segment)
272 lrs number of pages of library (always 0 on 2.6)
273 drs number of pages of data/stack (including libs; broken,
274 includes library text)
275 dt number of dirty pages (always 0 on 2.6)
276 ..............................................................................
279 Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
280 ..............................................................................
283 tcomm filename of the executable
284 state state (R is running, S is sleeping, D is sleeping in an
285 uninterruptible wait, Z is zombie, T is traced or stopped)
286 ppid process id of the parent process
287 pgrp pgrp of the process
289 tty_nr tty the process uses
290 tty_pgrp pgrp of the tty
292 min_flt number of minor faults
293 cmin_flt number of minor faults with child's
294 maj_flt number of major faults
295 cmaj_flt number of major faults with child's
296 utime user mode jiffies
297 stime kernel mode jiffies
298 cutime user mode jiffies with child's
299 cstime kernel mode jiffies with child's
300 priority priority level
302 num_threads number of threads
303 it_real_value (obsolete, always 0)
304 start_time time the process started after system boot
305 vsize virtual memory size
306 rss resident set memory size
307 rsslim current limit in bytes on the rss
308 start_code address above which program text can run
309 end_code address below which program text can run
310 start_stack address of the start of the main process stack
311 esp current value of ESP
312 eip current value of EIP
313 pending bitmap of pending signals
314 blocked bitmap of blocked signals
315 sigign bitmap of ignored signals
316 sigcatch bitmap of caught signals
317 0 (place holder, used to be the wchan address, use /proc/PID/wchan instead)
320 exit_signal signal to send to parent thread on exit
321 task_cpu which CPU the task is scheduled on
322 rt_priority realtime priority
323 policy scheduling policy (man sched_setscheduler)
324 blkio_ticks time spent waiting for block IO
325 gtime guest time of the task in jiffies
326 cgtime guest time of the task children in jiffies
327 start_data address above which program data+bss is placed
328 end_data address below which program data+bss is placed
329 start_brk address above which program heap can be expanded with brk()
330 arg_start address above which program command line is placed
331 arg_end address below which program command line is placed
332 env_start address above which program environment is placed
333 env_end address below which program environment is placed
334 exit_code the thread's exit_code in the form reported by the waitpid system call
335 ..............................................................................
337 The /proc/PID/maps file containing the currently mapped memory regions and
338 their access permissions.
342 address perms offset dev inode pathname
344 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test
345 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
346 0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
347 a7cb1000-a7cb2000 ---p 00000000 00:00 0
348 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
349 a7eb2000-a7eb3000 ---p 00000000 00:00 0
350 a7eb3000-a7ed5000 rw-p 00000000 00:00 0
351 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
352 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6
353 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6
354 a800b000-a800e000 rw-p 00000000 00:00 0
355 a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
356 a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
357 a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
358 a8024000-a8027000 rw-p 00000000 00:00 0
359 a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
360 a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
361 a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
362 aff35000-aff4a000 rw-p 00000000 00:00 0 [stack]
363 ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
365 where "address" is the address space in the process that it occupies, "perms"
366 is a set of permissions:
372 p = private (copy on write)
374 "offset" is the offset into the mapping, "dev" is the device (major:minor), and
375 "inode" is the inode on that device. 0 indicates that no inode is associated
376 with the memory region, as the case would be with BSS (uninitialized data).
377 The "pathname" shows the name associated file for this mapping. If the mapping
378 is not associated with a file:
380 [heap] = the heap of the program
381 [stack] = the stack of the main process
382 [vdso] = the "virtual dynamic shared object",
383 the kernel system call handler
384 [anon:<name>] = an anonymous mapping that has been
387 or if empty, the mapping is anonymous.
389 The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
390 of the individual tasks of a process. In this file you will see a mapping marked
391 as [stack] if that task sees it as a stack. Hence, for the example above, the
392 task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
394 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test
395 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
396 0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
397 a7cb1000-a7cb2000 ---p 00000000 00:00 0
398 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
399 a7eb2000-a7eb3000 ---p 00000000 00:00 0
400 a7eb3000-a7ed5000 rw-p 00000000 00:00 0 [stack]
401 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
402 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6
403 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6
404 a800b000-a800e000 rw-p 00000000 00:00 0
405 a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
406 a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
407 a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
408 a8024000-a8027000 rw-p 00000000 00:00 0
409 a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
410 a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
411 a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
412 aff35000-aff4a000 rw-p 00000000 00:00 0
413 ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
415 The /proc/PID/smaps is an extension based on maps, showing the memory
416 consumption for each of the process's mappings. For each of mappings there
417 is a series of lines such as the following:
419 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash
431 Private_Hugetlb: 0 kB
437 VmFlags: rd ex mr mw me dw
438 Name: name from userspace
440 the first of these lines shows the same information as is displayed for the
441 mapping in /proc/PID/maps. The remaining lines show the size of the mapping
442 (size), the amount of the mapping that is currently resident in RAM (RSS), the
443 process' proportional share of this mapping (PSS), the number of clean and
444 dirty private pages in the mapping.
446 The "proportional set size" (PSS) of a process is the count of pages it has
447 in memory, where each page is divided by the number of processes sharing it.
448 So if a process has 1000 pages all to itself, and 1000 shared with one other
449 process, its PSS will be 1500.
450 Note that even a page which is part of a MAP_SHARED mapping, but has only
451 a single pte mapped, i.e. is currently used by only one process, is accounted
452 as private and not as shared.
453 "Referenced" indicates the amount of memory currently marked as referenced or
455 "Anonymous" shows the amount of memory that does not belong to any file. Even
456 a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
457 and a page is modified, the file page is replaced by a private anonymous copy.
458 "AnonHugePages" shows the ammount of memory backed by transparent hugepage.
459 "Shared_Hugetlb" and "Private_Hugetlb" show the ammounts of memory backed by
460 hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical
461 reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field.
462 "Swap" shows how much would-be-anonymous memory is also used, but out on swap.
463 "SwapPss" shows proportional swap share of this mapping.
464 "Locked" indicates whether the mapping is locked in memory or not.
466 "VmFlags" field deserves a separate description. This member represents the kernel
467 flags associated with the particular virtual memory area in two letter encoded
468 manner. The codes are the following:
477 gd - stack segment growns down
479 dw - disabled write to the mapped file
480 lo - pages are locked in memory
481 io - memory mapped I/O area
482 sr - sequential read advise provided
483 rr - random read advise provided
484 dc - do not copy area on fork
485 de - do not expand area on remapping
486 ac - area is accountable
487 nr - swap space is not reserved for the area
488 ht - area uses huge tlb pages
489 ar - architecture specific flag
490 dd - do not include area into core dump
493 hg - huge page advise flag
494 nh - no-huge page advise flag
495 mg - mergable advise flag
497 Note that there is no guarantee that every flag and associated mnemonic will
498 be present in all further kernel releases. Things get changed, the flags may
499 be vanished or the reverse -- new added.
501 The "Name" field will only be present on a mapping that has been named by
502 userspace, and will show the name passed in by userspace.
504 This file is only present if the CONFIG_MMU kernel configuration option is
507 The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
508 bits on both physical and virtual pages associated with a process, and the
509 soft-dirty bit on pte (see Documentation/vm/soft-dirty.txt for details).
510 To clear the bits for all the pages associated with the process
511 > echo 1 > /proc/PID/clear_refs
513 To clear the bits for the anonymous pages associated with the process
514 > echo 2 > /proc/PID/clear_refs
516 To clear the bits for the file mapped pages associated with the process
517 > echo 3 > /proc/PID/clear_refs
519 To clear the soft-dirty bit
520 > echo 4 > /proc/PID/clear_refs
522 To reset the peak resident set size ("high water mark") to the process's
524 > echo 5 > /proc/PID/clear_refs
526 Any other value written to /proc/PID/clear_refs will have no effect.
528 The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
529 using /proc/kpageflags and number of times a page is mapped using
530 /proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
532 The /proc/pid/numa_maps is an extension based on maps, showing the memory
533 locality and binding policy, as well as the memory usage (in pages) of
534 each mapping. The output follows a general format where mapping details get
535 summarized separated by blank spaces, one mapping per each file line:
537 address policy mapping details
539 00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4
540 00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4
541 3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4
542 320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
543 3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
544 3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4
545 3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4
546 320698b000 default file=/lib64/libc-2.12.so
547 3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4
548 3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
549 3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4
550 7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4
551 7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4
552 7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048
553 7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4
554 7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4
557 "address" is the starting address for the mapping;
558 "policy" reports the NUMA memory policy set for the mapping (see vm/numa_memory_policy.txt);
559 "mapping details" summarizes mapping data such as mapping type, page usage counters,
560 node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page
561 size, in KB, that is backing the mapping up.
566 Similar to the process entries, the kernel data files give information about
567 the running kernel. The files used to obtain this information are contained in
568 /proc and are listed in Table 1-5. Not all of these will be present in your
569 system. It depends on the kernel configuration and the loaded modules, which
570 files are there, and which are missing.
572 Table 1-5: Kernel info in /proc
573 ..............................................................................
575 apm Advanced power management info
576 buddyinfo Kernel memory allocator information (see text) (2.5)
577 bus Directory containing bus specific information
578 cmdline Kernel command line
579 cpuinfo Info about the CPU
580 devices Available devices (block and character)
581 dma Used DMS channels
582 filesystems Supported filesystems
583 driver Various drivers grouped here, currently rtc (2.4)
584 execdomains Execdomains, related to security (2.4)
585 fb Frame Buffer devices (2.4)
586 fs File system parameters, currently nfs/exports (2.4)
587 ide Directory containing info about the IDE subsystem
588 interrupts Interrupt usage
589 iomem Memory map (2.4)
590 ioports I/O port usage
591 irq Masks for irq to cpu affinity (2.4)(smp?)
592 isapnp ISA PnP (Plug&Play) Info (2.4)
593 kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4))
595 ksyms Kernel symbol table
596 loadavg Load average of last 1, 5 & 15 minutes
600 modules List of loaded modules
601 mounts Mounted filesystems
602 net Networking info (see text)
603 pagetypeinfo Additional page allocator information (see text) (2.5)
604 partitions Table of partitions known to the system
605 pci Deprecated info of PCI bus (new way -> /proc/bus/pci/,
606 decoupled by lspci (2.4)
608 scsi SCSI info (see text)
609 slabinfo Slab pool info
610 softirqs softirq usage
611 stat Overall statistics
612 swaps Swap space utilization
614 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4)
615 tty Info of tty drivers
616 uptime Wall clock since boot, combined idle time of all cpus
617 version Kernel version
618 video bttv info of video resources (2.4)
619 vmallocinfo Show vmalloced areas
620 ..............................................................................
622 You can, for example, check which interrupts are currently in use and what
623 they are used for by looking in the file /proc/interrupts:
625 > cat /proc/interrupts
627 0: 8728810 XT-PIC timer
628 1: 895 XT-PIC keyboard
630 3: 531695 XT-PIC aha152x
631 4: 2014133 XT-PIC serial
632 5: 44401 XT-PIC pcnet_cs
635 12: 182918 XT-PIC PS/2 Mouse
637 14: 1232265 XT-PIC ide0
641 In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
642 output of a SMP machine):
644 > cat /proc/interrupts
647 0: 1243498 1214548 IO-APIC-edge timer
648 1: 8949 8958 IO-APIC-edge keyboard
649 2: 0 0 XT-PIC cascade
650 5: 11286 10161 IO-APIC-edge soundblaster
651 8: 1 0 IO-APIC-edge rtc
652 9: 27422 27407 IO-APIC-edge 3c503
653 12: 113645 113873 IO-APIC-edge PS/2 Mouse
655 14: 22491 24012 IO-APIC-edge ide0
656 15: 2183 2415 IO-APIC-edge ide1
657 17: 30564 30414 IO-APIC-level eth0
658 18: 177 164 IO-APIC-level bttv
663 NMI is incremented in this case because every timer interrupt generates a NMI
664 (Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups.
666 LOC is the local interrupt counter of the internal APIC of every CPU.
668 ERR is incremented in the case of errors in the IO-APIC bus (the bus that
669 connects the CPUs in a SMP system. This means that an error has been detected,
670 the IO-APIC automatically retry the transmission, so it should not be a big
671 problem, but you should read the SMP-FAQ.
673 In 2.6.2* /proc/interrupts was expanded again. This time the goal was for
674 /proc/interrupts to display every IRQ vector in use by the system, not
675 just those considered 'most important'. The new vectors are:
677 THR -- interrupt raised when a machine check threshold counter
678 (typically counting ECC corrected errors of memory or cache) exceeds
679 a configurable threshold. Only available on some systems.
681 TRM -- a thermal event interrupt occurs when a temperature threshold
682 has been exceeded for the CPU. This interrupt may also be generated
683 when the temperature drops back to normal.
685 SPU -- a spurious interrupt is some interrupt that was raised then lowered
686 by some IO device before it could be fully processed by the APIC. Hence
687 the APIC sees the interrupt but does not know what device it came from.
688 For this case the APIC will generate the interrupt with a IRQ vector
689 of 0xff. This might also be generated by chipset bugs.
691 RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
692 sent from one CPU to another per the needs of the OS. Typically,
693 their statistics are used by kernel developers and interested users to
694 determine the occurrence of interrupts of the given type.
696 The above IRQ vectors are displayed only when relevant. For example,
697 the threshold vector does not exist on x86_64 platforms. Others are
698 suppressed when the system is a uniprocessor. As of this writing, only
699 i386 and x86_64 platforms support the new IRQ vector displays.
701 Of some interest is the introduction of the /proc/irq directory to 2.4.
702 It could be used to set IRQ to CPU affinity, this means that you can "hook" an
703 IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
704 irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
709 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask
710 1 11 13 15 17 19 3 5 7 9 default_smp_affinity
714 smp_affinity is a bitmask, in which you can specify which CPUs can handle the
715 IRQ, you can set it by doing:
717 > echo 1 > /proc/irq/10/smp_affinity
719 This means that only the first CPU will handle the IRQ, but you can also echo
720 5 which means that only the first and fourth CPU can handle the IRQ.
722 The contents of each smp_affinity file is the same by default:
724 > cat /proc/irq/0/smp_affinity
727 There is an alternate interface, smp_affinity_list which allows specifying
728 a cpu range instead of a bitmask:
730 > cat /proc/irq/0/smp_affinity_list
733 The default_smp_affinity mask applies to all non-active IRQs, which are the
734 IRQs which have not yet been allocated/activated, and hence which lack a
735 /proc/irq/[0-9]* directory.
737 The node file on an SMP system shows the node to which the device using the IRQ
738 reports itself as being attached. This hardware locality information does not
739 include information about any possible driver locality preference.
741 prof_cpu_mask specifies which CPUs are to be profiled by the system wide
742 profiler. Default value is ffffffff (all cpus if there are only 32 of them).
744 The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
745 between all the CPUs which are allowed to handle it. As usual the kernel has
746 more info than you and does a better job than you, so the defaults are the
747 best choice for almost everyone. [Note this applies only to those IO-APIC's
748 that support "Round Robin" interrupt distribution.]
750 There are three more important subdirectories in /proc: net, scsi, and sys.
751 The general rule is that the contents, or even the existence of these
752 directories, depend on your kernel configuration. If SCSI is not enabled, the
753 directory scsi may not exist. The same is true with the net, which is there
754 only when networking support is present in the running kernel.
756 The slabinfo file gives information about memory usage at the slab level.
757 Linux uses slab pools for memory management above page level in version 2.2.
758 Commonly used objects have their own slab pool (such as network buffers,
759 directory cache, and so on).
761 ..............................................................................
763 > cat /proc/buddyinfo
765 Node 0, zone DMA 0 4 5 4 4 3 ...
766 Node 0, zone Normal 1 0 0 1 101 8 ...
767 Node 0, zone HighMem 2 0 0 1 1 0 ...
769 External fragmentation is a problem under some workloads, and buddyinfo is a
770 useful tool for helping diagnose these problems. Buddyinfo will give you a
771 clue as to how big an area you can safely allocate, or why a previous
774 Each column represents the number of pages of a certain order which are
775 available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
776 ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE
777 available in ZONE_NORMAL, etc...
779 More information relevant to external fragmentation can be found in
782 > cat /proc/pagetypeinfo
786 Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
787 Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0
788 Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0
789 Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2
790 Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0
791 Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0
792 Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9
793 Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0
794 Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452
795 Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0
796 Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0
798 Number of blocks type Unmovable Reclaimable Movable Reserve Isolate
799 Node 0, zone DMA 2 0 5 1 0
800 Node 0, zone DMA32 41 6 967 2 0
802 Fragmentation avoidance in the kernel works by grouping pages of different
803 migrate types into the same contiguous regions of memory called page blocks.
804 A page block is typically the size of the default hugepage size e.g. 2MB on
805 X86-64. By keeping pages grouped based on their ability to move, the kernel
806 can reclaim pages within a page block to satisfy a high-order allocation.
808 The pagetypinfo begins with information on the size of a page block. It
809 then gives the same type of information as buddyinfo except broken down
810 by migrate-type and finishes with details on how many page blocks of each
813 If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
814 from libhugetlbfs http://sourceforge.net/projects/libhugetlbfs/), one can
815 make an estimate of the likely number of huge pages that can be allocated
816 at a given point in time. All the "Movable" blocks should be allocatable
817 unless memory has been mlock()'d. Some of the Reclaimable blocks should
818 also be allocatable although a lot of filesystem metadata may have to be
819 reclaimed to achieve this.
821 ..............................................................................
825 Provides information about distribution and utilization of memory. This
826 varies by architecture and compile options. The following is from a
827 16GB PIII, which has highmem enabled. You may not have all of these fields.
831 MemTotal: 16344972 kB
833 MemAvailable: 14836172 kB
839 HighTotal: 15597528 kB
840 HighFree: 13629632 kB
850 SReclaimable: 159856 kB
851 SUnreclaim: 124508 kB
856 CommitLimit: 7669796 kB
857 Committed_AS: 100056 kB
858 VmallocTotal: 112216 kB
860 VmallocChunk: 111088 kB
861 AnonHugePages: 49152 kB
863 MemTotal: Total usable ram (i.e. physical ram minus a few reserved
864 bits and the kernel binary code)
865 MemFree: The sum of LowFree+HighFree
866 MemAvailable: An estimate of how much memory is available for starting new
867 applications, without swapping. Calculated from MemFree,
868 SReclaimable, the size of the file LRU lists, and the low
869 watermarks in each zone.
870 The estimate takes into account that the system needs some
871 page cache to function well, and that not all reclaimable
872 slab will be reclaimable, due to items being in use. The
873 impact of those factors will vary from system to system.
874 Buffers: Relatively temporary storage for raw disk blocks
875 shouldn't get tremendously large (20MB or so)
876 Cached: in-memory cache for files read from the disk (the
877 pagecache). Doesn't include SwapCached
878 SwapCached: Memory that once was swapped out, is swapped back in but
879 still also is in the swapfile (if memory is needed it
880 doesn't need to be swapped out AGAIN because it is already
881 in the swapfile. This saves I/O)
882 Active: Memory that has been used more recently and usually not
883 reclaimed unless absolutely necessary.
884 Inactive: Memory which has been less recently used. It is more
885 eligible to be reclaimed for other purposes
887 HighFree: Highmem is all memory above ~860MB of physical memory
888 Highmem areas are for use by userspace programs, or
889 for the pagecache. The kernel must use tricks to access
890 this memory, making it slower to access than lowmem.
892 LowFree: Lowmem is memory which can be used for everything that
893 highmem can be used for, but it is also available for the
894 kernel's use for its own data structures. Among many
895 other things, it is where everything from the Slab is
896 allocated. Bad things happen when you're out of lowmem.
897 SwapTotal: total amount of swap space available
898 SwapFree: Memory which has been evicted from RAM, and is temporarily
900 Dirty: Memory which is waiting to get written back to the disk
901 Writeback: Memory which is actively being written back to the disk
902 AnonPages: Non-file backed pages mapped into userspace page tables
903 AnonHugePages: Non-file backed huge pages mapped into userspace page tables
904 Mapped: files which have been mmaped, such as libraries
905 Slab: in-kernel data structures cache
906 SReclaimable: Part of Slab, that might be reclaimed, such as caches
907 SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure
908 PageTables: amount of memory dedicated to the lowest level of page
910 NFS_Unstable: NFS pages sent to the server, but not yet committed to stable
912 Bounce: Memory used for block device "bounce buffers"
913 WritebackTmp: Memory used by FUSE for temporary writeback buffers
914 CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'),
915 this is the total amount of memory currently available to
916 be allocated on the system. This limit is only adhered to
917 if strict overcommit accounting is enabled (mode 2 in
918 'vm.overcommit_memory').
919 The CommitLimit is calculated with the following formula:
920 CommitLimit = ([total RAM pages] - [total huge TLB pages]) *
921 overcommit_ratio / 100 + [total swap pages]
922 For example, on a system with 1G of physical RAM and 7G
923 of swap with a `vm.overcommit_ratio` of 30 it would
924 yield a CommitLimit of 7.3G.
925 For more details, see the memory overcommit documentation
926 in vm/overcommit-accounting.
927 Committed_AS: The amount of memory presently allocated on the system.
928 The committed memory is a sum of all of the memory which
929 has been allocated by processes, even if it has not been
930 "used" by them as of yet. A process which malloc()'s 1G
931 of memory, but only touches 300M of it will show up as
932 using 1G. This 1G is memory which has been "committed" to
933 by the VM and can be used at any time by the allocating
934 application. With strict overcommit enabled on the system
935 (mode 2 in 'vm.overcommit_memory'),allocations which would
936 exceed the CommitLimit (detailed above) will not be permitted.
937 This is useful if one needs to guarantee that processes will
938 not fail due to lack of memory once that memory has been
939 successfully allocated.
940 VmallocTotal: total size of vmalloc memory area
941 VmallocUsed: amount of vmalloc area which is used
942 VmallocChunk: largest contiguous block of vmalloc area which is free
944 ..............................................................................
948 Provides information about vmalloced/vmaped areas. One line per area,
949 containing the virtual address range of the area, size in bytes,
950 caller information of the creator, and optional information depending
951 on the kind of area :
953 pages=nr number of pages
954 phys=addr if a physical address was specified
955 ioremap I/O mapping (ioremap() and friends)
956 vmalloc vmalloc() area
959 vpages buffer for pages pointers was vmalloced (huge area)
960 N<node>=nr (Only on NUMA kernels)
961 Number of pages allocated on memory node <node>
963 > cat /proc/vmallocinfo
964 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
965 /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
966 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
967 /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
968 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f...
969 phys=7fee8000 ioremap
970 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f...
971 phys=7fee7000 ioremap
972 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210
973 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ...
974 /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
975 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ...
977 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ...
978 /0x130 [x_tables] pages=4 vmalloc N0=4
979 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ...
980 pages=14 vmalloc N2=14
981 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ...
983 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ...
985 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ...
986 pages=10 vmalloc N0=10
988 ..............................................................................
992 Provides counts of softirq handlers serviced since boot time, for each cpu.
997 TIMER: 27166 27120 27097 27034
1002 SCHED: 27035 26983 26971 26746
1004 RCU: 1678 1769 2178 2250
1007 1.3 IDE devices in /proc/ide
1008 ----------------------------
1010 The subdirectory /proc/ide contains information about all IDE devices of which
1011 the kernel is aware. There is one subdirectory for each IDE controller, the
1012 file drivers and a link for each IDE device, pointing to the device directory
1013 in the controller specific subtree.
1015 The file drivers contains general information about the drivers used for the
1018 > cat /proc/ide/drivers
1019 ide-cdrom version 4.53
1020 ide-disk version 1.08
1022 More detailed information can be found in the controller specific
1023 subdirectories. These are named ide0, ide1 and so on. Each of these
1024 directories contains the files shown in table 1-6.
1027 Table 1-6: IDE controller info in /proc/ide/ide?
1028 ..............................................................................
1030 channel IDE channel (0 or 1)
1031 config Configuration (only for PCI/IDE bridge)
1033 model Type/Chipset of IDE controller
1034 ..............................................................................
1036 Each device connected to a controller has a separate subdirectory in the
1037 controllers directory. The files listed in table 1-7 are contained in these
1041 Table 1-7: IDE device information
1042 ..............................................................................
1045 capacity Capacity of the medium (in 512Byte blocks)
1046 driver driver and version
1047 geometry physical and logical geometry
1048 identify device identify block
1050 model device identifier
1051 settings device setup
1052 smart_thresholds IDE disk management thresholds
1053 smart_values IDE disk management values
1054 ..............................................................................
1056 The most interesting file is settings. This file contains a nice overview of
1057 the drive parameters:
1059 # cat /proc/ide/ide0/hda/settings
1060 name value min max mode
1061 ---- ----- --- --- ----
1062 bios_cyl 526 0 65535 rw
1063 bios_head 255 0 255 rw
1064 bios_sect 63 0 63 rw
1065 breada_readahead 4 0 127 rw
1067 file_readahead 72 0 2097151 rw
1069 keepsettings 0 0 1 rw
1070 max_kb_per_request 122 1 127 rw
1074 pio_mode write-only 0 255 w
1080 1.4 Networking info in /proc/net
1081 --------------------------------
1083 The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the
1084 additional values you get for IP version 6 if you configure the kernel to
1085 support this. Table 1-9 lists the files and their meaning.
1088 Table 1-8: IPv6 info in /proc/net
1089 ..............................................................................
1091 udp6 UDP sockets (IPv6)
1092 tcp6 TCP sockets (IPv6)
1093 raw6 Raw device statistics (IPv6)
1094 igmp6 IP multicast addresses, which this host joined (IPv6)
1095 if_inet6 List of IPv6 interface addresses
1096 ipv6_route Kernel routing table for IPv6
1097 rt6_stats Global IPv6 routing tables statistics
1098 sockstat6 Socket statistics (IPv6)
1099 snmp6 Snmp data (IPv6)
1100 ..............................................................................
1103 Table 1-9: Network info in /proc/net
1104 ..............................................................................
1106 arp Kernel ARP table
1107 dev network devices with statistics
1108 dev_mcast the Layer2 multicast groups a device is listening too
1109 (interface index, label, number of references, number of bound
1111 dev_stat network device status
1112 ip_fwchains Firewall chain linkage
1113 ip_fwnames Firewall chain names
1114 ip_masq Directory containing the masquerading tables
1115 ip_masquerade Major masquerading table
1116 netstat Network statistics
1117 raw raw device statistics
1118 route Kernel routing table
1119 rpc Directory containing rpc info
1120 rt_cache Routing cache
1122 sockstat Socket statistics
1125 unix UNIX domain sockets
1126 wireless Wireless interface data (Wavelan etc)
1127 igmp IP multicast addresses, which this host joined
1128 psched Global packet scheduler parameters.
1129 netlink List of PF_NETLINK sockets
1130 ip_mr_vifs List of multicast virtual interfaces
1131 ip_mr_cache List of multicast routing cache
1132 ..............................................................................
1134 You can use this information to see which network devices are available in
1135 your system and how much traffic was routed over those devices:
1138 Inter-|Receive |[...
1139 face |bytes packets errs drop fifo frame compressed multicast|[...
1140 lo: 908188 5596 0 0 0 0 0 0 [...
1141 ppp0:15475140 20721 410 0 0 410 0 0 [...
1142 eth0: 614530 7085 0 0 0 0 0 1 [...
1145 ...] bytes packets errs drop fifo colls carrier compressed
1146 ...] 908188 5596 0 0 0 0 0 0
1147 ...] 1375103 17405 0 0 0 0 0 0
1148 ...] 1703981 5535 0 0 0 3 0 0
1150 In addition, each Channel Bond interface has its own directory. For
1151 example, the bond0 device will have a directory called /proc/net/bond0/.
1152 It will contain information that is specific to that bond, such as the
1153 current slaves of the bond, the link status of the slaves, and how
1154 many times the slaves link has failed.
1159 If you have a SCSI host adapter in your system, you'll find a subdirectory
1160 named after the driver for this adapter in /proc/scsi. You'll also see a list
1161 of all recognized SCSI devices in /proc/scsi:
1163 >cat /proc/scsi/scsi
1165 Host: scsi0 Channel: 00 Id: 00 Lun: 00
1166 Vendor: IBM Model: DGHS09U Rev: 03E0
1167 Type: Direct-Access ANSI SCSI revision: 03
1168 Host: scsi0 Channel: 00 Id: 06 Lun: 00
1169 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04
1170 Type: CD-ROM ANSI SCSI revision: 02
1173 The directory named after the driver has one file for each adapter found in
1174 the system. These files contain information about the controller, including
1175 the used IRQ and the IO address range. The amount of information shown is
1176 dependent on the adapter you use. The example shows the output for an Adaptec
1177 AHA-2940 SCSI adapter:
1179 > cat /proc/scsi/aic7xxx/0
1181 Adaptec AIC7xxx driver version: 5.1.19/3.2.4
1183 TCQ Enabled By Default : Disabled
1184 AIC7XXX_PROC_STATS : Disabled
1185 AIC7XXX_RESET_DELAY : 5
1186 Adapter Configuration:
1187 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter
1188 Ultra Wide Controller
1189 PCI MMAPed I/O Base: 0xeb001000
1190 Adapter SEEPROM Config: SEEPROM found and used.
1191 Adaptec SCSI BIOS: Enabled
1193 SCBs: Active 0, Max Active 2,
1194 Allocated 15, HW 16, Page 255
1196 BIOS Control Word: 0x18b6
1197 Adapter Control Word: 0x005b
1198 Extended Translation: Enabled
1199 Disconnect Enable Flags: 0xffff
1200 Ultra Enable Flags: 0x0001
1201 Tag Queue Enable Flags: 0x0000
1202 Ordered Queue Tag Flags: 0x0000
1203 Default Tag Queue Depth: 8
1204 Tagged Queue By Device array for aic7xxx host instance 0:
1205 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255}
1206 Actual queue depth per device for aic7xxx host instance 0:
1207 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}
1210 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8
1211 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0)
1212 Total transfers 160151 (74577 reads and 85574 writes)
1214 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15
1215 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0)
1216 Total transfers 0 (0 reads and 0 writes)
1219 1.6 Parallel port info in /proc/parport
1220 ---------------------------------------
1222 The directory /proc/parport contains information about the parallel ports of
1223 your system. It has one subdirectory for each port, named after the port
1226 These directories contain the four files shown in Table 1-10.
1229 Table 1-10: Files in /proc/parport
1230 ..............................................................................
1232 autoprobe Any IEEE-1284 device ID information that has been acquired.
1233 devices list of the device drivers using that port. A + will appear by the
1234 name of the device currently using the port (it might not appear
1236 hardware Parallel port's base address, IRQ line and DMA channel.
1237 irq IRQ that parport is using for that port. This is in a separate
1238 file to allow you to alter it by writing a new value in (IRQ
1240 ..............................................................................
1242 1.7 TTY info in /proc/tty
1243 -------------------------
1245 Information about the available and actually used tty's can be found in the
1246 directory /proc/tty.You'll find entries for drivers and line disciplines in
1247 this directory, as shown in Table 1-11.
1250 Table 1-11: Files in /proc/tty
1251 ..............................................................................
1253 drivers list of drivers and their usage
1254 ldiscs registered line disciplines
1255 driver/serial usage statistic and status of single tty lines
1256 ..............................................................................
1258 To see which tty's are currently in use, you can simply look into the file
1261 > cat /proc/tty/drivers
1262 pty_slave /dev/pts 136 0-255 pty:slave
1263 pty_master /dev/ptm 128 0-255 pty:master
1264 pty_slave /dev/ttyp 3 0-255 pty:slave
1265 pty_master /dev/pty 2 0-255 pty:master
1266 serial /dev/cua 5 64-67 serial:callout
1267 serial /dev/ttyS 4 64-67 serial
1268 /dev/tty0 /dev/tty0 4 0 system:vtmaster
1269 /dev/ptmx /dev/ptmx 5 2 system
1270 /dev/console /dev/console 5 1 system:console
1271 /dev/tty /dev/tty 5 0 system:/dev/tty
1272 unknown /dev/tty 4 1-63 console
1275 1.8 Miscellaneous kernel statistics in /proc/stat
1276 -------------------------------------------------
1278 Various pieces of information about kernel activity are available in the
1279 /proc/stat file. All of the numbers reported in this file are aggregates
1280 since the system first booted. For a quick look, simply cat the file:
1283 cpu 2255 34 2290 22625563 6290 127 456 0 0 0
1284 cpu0 1132 34 1441 11311718 3675 127 438 0 0 0
1285 cpu1 1123 0 849 11313845 2614 0 18 0 0 0
1286 intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...]
1292 softirq 183433 0 21755 12 39 1137 231 21459 2263
1294 The very first "cpu" line aggregates the numbers in all of the other "cpuN"
1295 lines. These numbers identify the amount of time the CPU has spent performing
1296 different kinds of work. Time units are in USER_HZ (typically hundredths of a
1297 second). The meanings of the columns are as follows, from left to right:
1299 - user: normal processes executing in user mode
1300 - nice: niced processes executing in user mode
1301 - system: processes executing in kernel mode
1302 - idle: twiddling thumbs
1303 - iowait: waiting for I/O to complete
1304 - irq: servicing interrupts
1305 - softirq: servicing softirqs
1306 - steal: involuntary wait
1307 - guest: running a normal guest
1308 - guest_nice: running a niced guest
1310 The "intr" line gives counts of interrupts serviced since boot time, for each
1311 of the possible system interrupts. The first column is the total of all
1312 interrupts serviced including unnumbered architecture specific interrupts;
1313 each subsequent column is the total for that particular numbered interrupt.
1314 Unnumbered interrupts are not shown, only summed into the total.
1316 The "ctxt" line gives the total number of context switches across all CPUs.
1318 The "btime" line gives the time at which the system booted, in seconds since
1321 The "processes" line gives the number of processes and threads created, which
1322 includes (but is not limited to) those created by calls to the fork() and
1323 clone() system calls.
1325 The "procs_running" line gives the total number of threads that are
1326 running or ready to run (i.e., the total number of runnable threads).
1328 The "procs_blocked" line gives the number of processes currently blocked,
1329 waiting for I/O to complete.
1331 The "softirq" line gives counts of softirqs serviced since boot time, for each
1332 of the possible system softirqs. The first column is the total of all
1333 softirqs serviced; each subsequent column is the total for that particular
1337 1.9 Ext4 file system parameters
1338 -------------------------------
1340 Information about mounted ext4 file systems can be found in
1341 /proc/fs/ext4. Each mounted filesystem will have a directory in
1342 /proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
1343 /proc/fs/ext4/dm-0). The files in each per-device directory are shown
1344 in Table 1-12, below.
1346 Table 1-12: Files in /proc/fs/ext4/<devname>
1347 ..............................................................................
1349 mb_groups details of multiblock allocator buddy cache of free blocks
1350 ..............................................................................
1354 Shows registered system console lines.
1356 To see which character device lines are currently used for the system console
1357 /dev/console, you may simply look into the file /proc/consoles:
1359 > cat /proc/consoles
1365 device name of the device
1366 operations R = can do read operations
1367 W = can do write operations
1369 flags E = it is enabled
1370 C = it is preferred console
1371 B = it is primary boot console
1372 p = it is used for printk buffer
1373 b = it is not a TTY but a Braille device
1374 a = it is safe to use when cpu is offline
1375 major:minor major and minor number of the device separated by a colon
1377 ------------------------------------------------------------------------------
1379 ------------------------------------------------------------------------------
1380 The /proc file system serves information about the running system. It not only
1381 allows access to process data but also allows you to request the kernel status
1382 by reading files in the hierarchy.
1384 The directory structure of /proc reflects the types of information and makes
1385 it easy, if not obvious, where to look for specific data.
1386 ------------------------------------------------------------------------------
1388 ------------------------------------------------------------------------------
1389 CHAPTER 2: MODIFYING SYSTEM PARAMETERS
1390 ------------------------------------------------------------------------------
1392 ------------------------------------------------------------------------------
1394 ------------------------------------------------------------------------------
1395 * Modifying kernel parameters by writing into files found in /proc/sys
1396 * Exploring the files which modify certain parameters
1397 * Review of the /proc/sys file tree
1398 ------------------------------------------------------------------------------
1401 A very interesting part of /proc is the directory /proc/sys. This is not only
1402 a source of information, it also allows you to change parameters within the
1403 kernel. Be very careful when attempting this. You can optimize your system,
1404 but you can also cause it to crash. Never alter kernel parameters on a
1405 production system. Set up a development machine and test to make sure that
1406 everything works the way you want it to. You may have no alternative but to
1407 reboot the machine once an error has been made.
1409 To change a value, simply echo the new value into the file. An example is
1410 given below in the section on the file system data. You need to be root to do
1411 this. You can create your own boot script to perform this every time your
1414 The files in /proc/sys can be used to fine tune and monitor miscellaneous and
1415 general things in the operation of the Linux kernel. Since some of the files
1416 can inadvertently disrupt your system, it is advisable to read both
1417 documentation and source before actually making adjustments. In any case, be
1418 very careful when writing to any of these files. The entries in /proc may
1419 change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
1420 review the kernel documentation in the directory /usr/src/linux/Documentation.
1421 This chapter is heavily based on the documentation included in the pre 2.2
1422 kernels, and became part of it in version 2.2.1 of the Linux kernel.
1424 Please see: Documentation/sysctl/ directory for descriptions of these
1427 ------------------------------------------------------------------------------
1429 ------------------------------------------------------------------------------
1430 Certain aspects of kernel behavior can be modified at runtime, without the
1431 need to recompile the kernel, or even to reboot the system. The files in the
1432 /proc/sys tree can not only be read, but also modified. You can use the echo
1433 command to write value into these files, thereby changing the default settings
1435 ------------------------------------------------------------------------------
1437 ------------------------------------------------------------------------------
1438 CHAPTER 3: PER-PROCESS PARAMETERS
1439 ------------------------------------------------------------------------------
1441 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
1442 --------------------------------------------------------------------------------
1444 These file can be used to adjust the badness heuristic used to select which
1445 process gets killed in out of memory conditions.
1447 The badness heuristic assigns a value to each candidate task ranging from 0
1448 (never kill) to 1000 (always kill) to determine which process is targeted. The
1449 units are roughly a proportion along that range of allowed memory the process
1450 may allocate from based on an estimation of its current memory and swap use.
1451 For example, if a task is using all allowed memory, its badness score will be
1452 1000. If it is using half of its allowed memory, its score will be 500.
1454 There is an additional factor included in the badness score: the current memory
1455 and swap usage is discounted by 3% for root processes.
1457 The amount of "allowed" memory depends on the context in which the oom killer
1458 was called. If it is due to the memory assigned to the allocating task's cpuset
1459 being exhausted, the allowed memory represents the set of mems assigned to that
1460 cpuset. If it is due to a mempolicy's node(s) being exhausted, the allowed
1461 memory represents the set of mempolicy nodes. If it is due to a memory
1462 limit (or swap limit) being reached, the allowed memory is that configured
1463 limit. Finally, if it is due to the entire system being out of memory, the
1464 allowed memory represents all allocatable resources.
1466 The value of /proc/<pid>/oom_score_adj is added to the badness score before it
1467 is used to determine which task to kill. Acceptable values range from -1000
1468 (OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX). This allows userspace to
1469 polarize the preference for oom killing either by always preferring a certain
1470 task or completely disabling it. The lowest possible value, -1000, is
1471 equivalent to disabling oom killing entirely for that task since it will always
1472 report a badness score of 0.
1474 Consequently, it is very simple for userspace to define the amount of memory to
1475 consider for each task. Setting a /proc/<pid>/oom_score_adj value of +500, for
1476 example, is roughly equivalent to allowing the remainder of tasks sharing the
1477 same system, cpuset, mempolicy, or memory controller resources to use at least
1478 50% more memory. A value of -500, on the other hand, would be roughly
1479 equivalent to discounting 50% of the task's allowed memory from being considered
1480 as scoring against the task.
1482 For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also
1483 be used to tune the badness score. Its acceptable values range from -16
1484 (OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17
1485 (OOM_DISABLE) to disable oom killing entirely for that task. Its value is
1486 scaled linearly with /proc/<pid>/oom_score_adj.
1488 The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last
1489 value set by a CAP_SYS_RESOURCE process. To reduce the value any lower
1490 requires CAP_SYS_RESOURCE.
1492 Caveat: when a parent task is selected, the oom killer will sacrifice any first
1493 generation children with separate address spaces instead, if possible. This
1494 avoids servers and important system daemons from being killed and loses the
1495 minimal amount of work.
1498 3.2 /proc/<pid>/oom_score - Display current oom-killer score
1499 -------------------------------------------------------------
1501 This file can be used to check the current score used by the oom-killer is for
1502 any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which
1503 process should be killed in an out-of-memory situation.
1506 3.3 /proc/<pid>/io - Display the IO accounting fields
1507 -------------------------------------------------------
1509 This file contains IO statistics for each running process
1514 test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
1517 test:/tmp # cat /proc/3828/io
1523 write_bytes: 323932160
1524 cancelled_write_bytes: 0
1533 I/O counter: chars read
1534 The number of bytes which this task has caused to be read from storage. This
1535 is simply the sum of bytes which this process passed to read() and pread().
1536 It includes things like tty IO and it is unaffected by whether or not actual
1537 physical disk IO was required (the read might have been satisfied from
1544 I/O counter: chars written
1545 The number of bytes which this task has caused, or shall cause to be written
1546 to disk. Similar caveats apply here as with rchar.
1552 I/O counter: read syscalls
1553 Attempt to count the number of read I/O operations, i.e. syscalls like read()
1560 I/O counter: write syscalls
1561 Attempt to count the number of write I/O operations, i.e. syscalls like
1562 write() and pwrite().
1568 I/O counter: bytes read
1569 Attempt to count the number of bytes which this process really did cause to
1570 be fetched from the storage layer. Done at the submit_bio() level, so it is
1571 accurate for block-backed filesystems. <please add status regarding NFS and
1572 CIFS at a later time>
1578 I/O counter: bytes written
1579 Attempt to count the number of bytes which this process caused to be sent to
1580 the storage layer. This is done at page-dirtying time.
1583 cancelled_write_bytes
1584 ---------------------
1586 The big inaccuracy here is truncate. If a process writes 1MB to a file and
1587 then deletes the file, it will in fact perform no writeout. But it will have
1588 been accounted as having caused 1MB of write.
1589 In other words: The number of bytes which this process caused to not happen,
1590 by truncating pagecache. A task can cause "negative" IO too. If this task
1591 truncates some dirty pagecache, some IO which another task has been accounted
1592 for (in its write_bytes) will not be happening. We _could_ just subtract that
1593 from the truncating task's write_bytes, but there is information loss in doing
1600 At its current implementation state, this is a bit racy on 32-bit machines: if
1601 process A reads process B's /proc/pid/io while process B is updating one of
1602 those 64-bit counters, process A could see an intermediate result.
1605 More information about this can be found within the taskstats documentation in
1606 Documentation/accounting.
1608 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
1609 ---------------------------------------------------------------
1610 When a process is dumped, all anonymous memory is written to a core file as
1611 long as the size of the core file isn't limited. But sometimes we don't want
1612 to dump some memory segments, for example, huge shared memory or DAX.
1613 Conversely, sometimes we want to save file-backed memory segments into a core
1614 file, not only the individual files.
1616 /proc/<pid>/coredump_filter allows you to customize which memory segments
1617 will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
1618 of memory types. If a bit of the bitmask is set, memory segments of the
1619 corresponding memory type are dumped, otherwise they are not dumped.
1621 The following 9 memory types are supported:
1622 - (bit 0) anonymous private memory
1623 - (bit 1) anonymous shared memory
1624 - (bit 2) file-backed private memory
1625 - (bit 3) file-backed shared memory
1626 - (bit 4) ELF header pages in file-backed private memory areas (it is
1627 effective only if the bit 2 is cleared)
1628 - (bit 5) hugetlb private memory
1629 - (bit 6) hugetlb shared memory
1630 - (bit 7) DAX private memory
1631 - (bit 8) DAX shared memory
1633 Note that MMIO pages such as frame buffer are never dumped and vDSO pages
1634 are always dumped regardless of the bitmask status.
1636 Note that bits 0-4 don't affect hugetlb or DAX memory. hugetlb memory is
1637 only affected by bit 5-6, and DAX is only affected by bits 7-8.
1639 The default value of coredump_filter is 0x33; this means all anonymous memory
1640 segments, ELF header pages and hugetlb private memory are dumped.
1642 If you don't want to dump all shared memory segments attached to pid 1234,
1643 write 0x31 to the process's proc file.
1645 $ echo 0x31 > /proc/1234/coredump_filter
1647 When a new process is created, the process inherits the bitmask status from its
1648 parent. It is useful to set up coredump_filter before the program runs.
1651 $ echo 0x7 > /proc/self/coredump_filter
1654 3.5 /proc/<pid>/mountinfo - Information about mounts
1655 --------------------------------------------------------
1657 This file contains lines of the form:
1659 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
1660 (1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11)
1662 (1) mount ID: unique identifier of the mount (may be reused after umount)
1663 (2) parent ID: ID of parent (or of self for the top of the mount tree)
1664 (3) major:minor: value of st_dev for files on filesystem
1665 (4) root: root of the mount within the filesystem
1666 (5) mount point: mount point relative to the process's root
1667 (6) mount options: per mount options
1668 (7) optional fields: zero or more fields of the form "tag[:value]"
1669 (8) separator: marks the end of the optional fields
1670 (9) filesystem type: name of filesystem of the form "type[.subtype]"
1671 (10) mount source: filesystem specific information or "none"
1672 (11) super options: per super block options
1674 Parsers should ignore all unrecognised optional fields. Currently the
1675 possible optional fields are:
1677 shared:X mount is shared in peer group X
1678 master:X mount is slave to peer group X
1679 propagate_from:X mount is slave and receives propagation from peer group X (*)
1680 unbindable mount is unbindable
1682 (*) X is the closest dominant peer group under the process's root. If
1683 X is the immediate master of the mount, or if there's no dominant peer
1684 group under the same root, then only the "master:X" field is present
1685 and not the "propagate_from:X" field.
1687 For more information on mount propagation see:
1689 Documentation/filesystems/sharedsubtree.txt
1692 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm
1693 --------------------------------------------------------
1694 These files provide a method to access a tasks comm value. It also allows for
1695 a task to set its own or one of its thread siblings comm value. The comm value
1696 is limited in size compared to the cmdline value, so writing anything longer
1697 then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated
1701 3.7 /proc/<pid>/task/<tid>/children - Information about task children
1702 -------------------------------------------------------------------------
1703 This file provides a fast way to retrieve first level children pids
1704 of a task pointed by <pid>/<tid> pair. The format is a space separated
1707 Note the "first level" here -- if a child has own children they will
1708 not be listed here, one needs to read /proc/<children-pid>/task/<tid>/children
1709 to obtain the descendants.
1711 Since this interface is intended to be fast and cheap it doesn't
1712 guarantee to provide precise results and some children might be
1713 skipped, especially if they've exited right after we printed their
1714 pids, so one need to either stop or freeze processes being inspected
1715 if precise results are needed.
1718 3.8 /proc/<pid>/fdinfo/<fd> - Information about opened file
1719 ---------------------------------------------------------------
1720 This file provides information associated with an opened file. The regular
1721 files have at least three fields -- 'pos', 'flags' and mnt_id. The 'pos'
1722 represents the current offset of the opened file in decimal form [see lseek(2)
1723 for details], 'flags' denotes the octal O_xxx mask the file has been
1724 created with [see open(2) for details] and 'mnt_id' represents mount ID of
1725 the file system containing the opened file [see 3.5 /proc/<pid>/mountinfo
1734 All locks associated with a file descriptor are shown in its fdinfo too.
1736 lock: 1: FLOCK ADVISORY WRITE 359 00:13:11691 0 EOF
1738 The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
1739 pair provide additional information particular to the objects they represent.
1748 where 'eventfd-count' is hex value of a counter.
1755 sigmask: 0000000000000200
1757 where 'sigmask' is hex value of the signal mask associated
1765 tfd: 5 events: 1d data: ffffffffffffffff
1767 where 'tfd' is a target file descriptor number in decimal form,
1768 'events' is events mask being watched and the 'data' is data
1769 associated with a target [see epoll(7) for more details].
1773 For inotify files the format is the following
1777 inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d
1779 where 'wd' is a watch descriptor in decimal form, ie a target file
1780 descriptor number, 'ino' and 'sdev' are inode and device where the
1781 target file resides and the 'mask' is the mask of events, all in hex
1782 form [see inotify(7) for more details].
1784 If the kernel was built with exportfs support, the path to the target
1785 file is encoded as a file handle. The file handle is provided by three
1786 fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex
1789 If the kernel is built without exportfs support the file handle won't be
1792 If there is no inotify mark attached yet the 'inotify' line will be omitted.
1794 For fanotify files the format is
1799 fanotify flags:10 event-flags:0
1800 fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003
1801 fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4
1803 where fanotify 'flags' and 'event-flags' are values used in fanotify_init
1804 call, 'mnt_id' is the mount point identifier, 'mflags' is the value of
1805 flags associated with mark which are tracked separately from events
1806 mask. 'ino', 'sdev' are target inode and device, 'mask' is the events
1807 mask and 'ignored_mask' is the mask of events which are to be ignored.
1808 All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask'
1809 does provide information about flags and mask used in fanotify_mark
1810 call [see fsnotify manpage for details].
1812 While the first three lines are mandatory and always printed, the rest is
1813 optional and may be omitted if no marks created yet.
1824 it_value: (0, 49406829)
1827 where 'clockid' is the clock type and 'ticks' is the number of the timer expirations
1828 that have occurred [see timerfd_create(2) for details]. 'settime flags' are
1829 flags in octal form been used to setup the timer [see timerfd_settime(2) for
1830 details]. 'it_value' is remaining time until the timer exiration.
1831 'it_interval' is the interval for the timer. Note the timer might be set up
1832 with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value'
1833 still exhibits timer's remaining time.
1835 3.9 /proc/<pid>/map_files - Information about memory mapped files
1836 ---------------------------------------------------------------------
1837 This directory contains symbolic links which represent memory mapped files
1838 the process is maintaining. Example output:
1840 | lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so
1841 | lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so
1842 | lr-------- 1 root root 64 Jan 27 11:24 333c820000-333c821000 -> /usr/lib64/ld-2.18.so
1844 | lr-------- 1 root root 64 Jan 27 11:24 35d0421000-35d0422000 -> /usr/lib64/libselinux.so.1
1845 | lr-------- 1 root root 64 Jan 27 11:24 400000-41a000 -> /usr/bin/ls
1847 The name of a link represents the virtual memory bounds of a mapping, i.e.
1848 vm_area_struct::vm_start-vm_area_struct::vm_end.
1850 The main purpose of the map_files is to retrieve a set of memory mapped
1851 files in a fast way instead of parsing /proc/<pid>/maps or
1852 /proc/<pid>/smaps, both of which contain many more records. At the same
1853 time one can open(2) mappings from the listings of two processes and
1854 comparing their inode numbers to figure out which anonymous memory areas
1855 are actually shared.
1857 3.10 /proc/<pid>/timerslack_ns - Task timerslack value
1858 ---------------------------------------------------------
1859 This file provides the value of the task's timerslack value in nanoseconds.
1860 This value specifies a amount of time that normal timers may be deferred
1861 in order to coalesce timers and avoid unnecessary wakeups.
1863 This allows a task's interactivity vs power consumption trade off to be
1866 Writing 0 to the file will set the tasks timerslack to the default value.
1868 Valid values are from 0 - ULLONG_MAX
1870 An application setting the value must have PTRACE_MODE_ATTACH_FSCREDS level
1871 permissions on the task specified to change its timerslack_ns value.
1874 ------------------------------------------------------------------------------
1876 ------------------------------------------------------------------------------
1879 ---------------------
1881 The following mount options are supported:
1883 hidepid= Set /proc/<pid>/ access mode.
1884 gid= Set the group authorized to learn processes information.
1886 hidepid=0 means classic mode - everybody may access all /proc/<pid>/ directories
1889 hidepid=1 means users may not access any /proc/<pid>/ directories but their
1890 own. Sensitive files like cmdline, sched*, status are now protected against
1891 other users. This makes it impossible to learn whether any user runs
1892 specific program (given the program doesn't reveal itself by its behaviour).
1893 As an additional bonus, as /proc/<pid>/cmdline is unaccessible for other users,
1894 poorly written programs passing sensitive information via program arguments are
1895 now protected against local eavesdroppers.
1897 hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be fully invisible to other
1898 users. It doesn't mean that it hides a fact whether a process with a specific
1899 pid value exists (it can be learned by other means, e.g. by "kill -0 $PID"),
1900 but it hides process' uid and gid, which may be learned by stat()'ing
1901 /proc/<pid>/ otherwise. It greatly complicates an intruder's task of gathering
1902 information about running processes, whether some daemon runs with elevated
1903 privileges, whether other user runs some sensitive program, whether other users
1904 run any program at all, etc.
1906 gid= defines a group authorized to learn processes information otherwise
1907 prohibited by hidepid=. If you use some daemon like identd which needs to learn
1908 information about processes information, just add identd to this group.